patrickvonplaten
/

opt_metaseq_6700m

Feature Extraction

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

opt_metaseq_6700m / run.sh

patrickvonplaten's picture

patrickvonplaten

add model

7a9344a about 2 years ago

raw history blame contribute delete

No virus

133 Bytes

	#!/usr/bin/env bash
	CUDA_VISIBLE_DEVICES="0,3" torchrun run_model.py --pipeline-model-parallel-size 1 --tensor-model-parallel-size 1